Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Tencent Hunyuan open-sources Hy-SimulMT for real-time speech translation

AI summary

Tencent Hunyuan released and open-sourced Hy-SimulMT, a 30B model for bidirectional Chinese-English speech-to-speech simultaneous translation. The model processes audio while a speaker is talking, outputs translated text and speech, and supports real-time voice cloning; base, FP8, GGUF, and Interleave variants are available under Apache 2.0. Tencent Hunyuan also offers a trial through the Hy Translate App and provides the SimulInfer inference service and SimulTrain training tools.

In-depth insight

Hy-SimulMT combines open-weight access, streaming speech translation, voice cloning, and app availability in one release, giving developers tools for live bilingual meetings, interviews, and speeches.

tencent/Hy-SimulMT-30B-A3B-GGUF 30B • Updated 23 days ago • 6.62k • 13

English | 简体中文

Tencent Hy
Hy-SimulMT

A Low-Latency, High-Quality Model for Real-Time Simultaneous Translation

Introduction

Hy-SimulMT is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting bidirectional speech-to-speech translation between Chinese and English. It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech. With real-time voice cloning, it preserves the speaker's vocal characteristics while conveying the message accurately.

#Tencent Hunyuan#Hy-SimulMT-30B-A3B#Hy Translate App#SimulInfer#SimulTrain

Original · 12 min readRead the original
Group chat

No comments yet. Start the conversation.